© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13812
    Prev
    Next
    INDEX
    Explanations

    reasons, motivations

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that introduce or enumerate reasons or motivations (e.g., “reasons,” “myriad,” “to” in lists of causes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aktu
    -0.08
    ,O
    -0.06
    ость
    -0.06
     metre
    -0.06
    UGINS
    -0.06
    iors
    -0.06
    CHANT
    -0.06
    icians
    -0.06
     BRE
    -0.06
     Их
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵
    0.06
     personalized
    0.06
                        ↵
    0.06
     Shr
    0.06
    _example
    0.06
     прекрас
    0.06
    ى
    0.06
     etmiş
    0.06
    515
    0.06
    mektedir
    0.06
    Activations Density 0.049%

    No Known Activations